Answer-quality eval (LLM-judge) + hy3-led OpenRouter default (#81)

Add the agentic benchmark: coverage via citations, agentic vs single-shot

Add the v1 eval dataset: 100 valid + 100 invalid + 20 agentic

Add a retrieval benchmark: recall@k + MRR over the v0 questions

Codebase quality pass: kill silent-truncation hacks, fix latent bugs, cover them (#46)

Fix LLM transport drift, wire live static checks, clean config (#39)

Close M1: full 15/15 baseline, two fabrication findings, checker fix

Fix static checks for real-world answers: dedent code blocks, alias-aware symbols

M1: Answer schema, LLM wrapper with retry+repair, static checks, 15-question eval

Scaffold repo structure per M0 (pyproject, ruff, pytest, pre-commit)